Features
Photo-based object recognition for artworks, landmarks, and buildings
Instant audio storytelling (2–20 minutes depth)
Museum detection with deep analysis (composition, symbolism, backstory)
Context-aware AI chat for follow-up questions
Bilingual landmark names (English + local language)
Travel talks for planning your day
Local secrets and insider recommendations
Tap to navigate in Google Maps
Save favorites with a heart button
Offline photo library support
198B-A11B mixture-of-experts architecture
Vision-language understanding and generation
Fast inference for agent tool-use tasks
Multi-turn function calling support
Large context window for agent loops
Open-source model weights on HuggingFace
Strong multimodal reasoning and visual QA
High throughput per GPU with sparse activation
Customizable system prompts for agent behavior
Low-latency callback API design
Step-2 1.5B-step reasoning model on GitHub
